fin separation front/back

This commit is contained in:
hugo.pradier2
2024-06-23 17:44:26 +02:00
parent 15e1674cb2
commit 7dafa78bc4
13 changed files with 201 additions and 131 deletions

View File

@@ -0,0 +1,45 @@
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder
def perform_classification(data, data_name, target_name, test_size):
X = data[data_name]
y = data[target_name]
label_encoders = {}
for column in X.select_dtypes(include=['object']).columns:
le = LabelEncoder()
X[column] = le.fit_transform(X[column])
label_encoders[column] = le
if y.dtype == 'object':
le = LabelEncoder()
y = le.fit_transform(y)
label_encoders[target_name] = le
else:
if y.nunique() > 10:
raise ValueError("The target variable seems to be continuous. Please select a categorical target for classification.")
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=42)
model = LogisticRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
return model, label_encoders, accuracy
def make_prediction(model, label_encoders, data_name, target_name, input_values):
X_new = []
for feature, value in zip(data_name, input_values):
if feature in label_encoders:
value = label_encoders[feature].transform([value])[0]
X_new.append(value)
prediction = model.predict([X_new])
if target_name in label_encoders:
prediction = label_encoders[target_name].inverse_transform(prediction)
return prediction[0]

View File

@@ -0,0 +1,17 @@
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import DBSCAN
def perform_dbscan_clustering(data, data_name, eps, min_samples):
x = data[data_name].to_numpy()
dbscan = DBSCAN(eps=eps, min_samples=min_samples)
y_dbscan = dbscan.fit_predict(x)
fig = plt.figure()
if len(data_name) == 2:
ax = fig.add_subplot(projection='rectilinear')
plt.scatter(x[:, 0], x[:, 1], c=y_dbscan, s=50, cmap="viridis")
else:
ax = fig.add_subplot(projection='3d')
ax.scatter(x[:, 0], x[:, 1], x[:, 2], c=y_dbscan, s=50, cmap="viridis")
return fig

View File

@@ -0,0 +1,21 @@
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
def perform_kmeans_clustering(data, data_name, n_clusters, n_init, max_iter):
x = data[data_name].to_numpy()
kmeans = KMeans(n_clusters=n_clusters, init="random", n_init=n_init, max_iter=max_iter, random_state=111)
y_kmeans = kmeans.fit_predict(x)
fig = plt.figure()
if len(data_name) == 2:
ax = fig.add_subplot(projection='rectilinear')
plt.scatter(x[:, 0], x[:, 1], c=y_kmeans, s=50, cmap="viridis")
centers = kmeans.cluster_centers_
plt.scatter(centers[:, 0], centers[:, 1], c="black", s=200, marker="X")
else:
ax = fig.add_subplot(projection='3d')
ax.scatter(x[:, 0], x[:, 1], x[:, 2], c=y_kmeans, s=50, cmap="viridis")
centers = kmeans.cluster_centers_
ax.scatter(centers[:, 0], centers[:, 1], centers[:, 2], c="black", s=200, marker="X")
return fig

View File

@@ -0,0 +1,18 @@
from sklearn.linear_model import LinearRegression
def perform_regression(data, data_name, target_name):
X = data[data_name]
y = data[target_name]
if not isinstance(y.iloc[0], (int, float)):
raise ValueError("The target variable should be numeric (continuous) for regression.")
model = LinearRegression()
model.fit(X, y)
return model
def make_prediction(model, feature_names, input_values):
prediction = model.predict([input_values])
return prediction[0]

View File

@@ -0,0 +1,16 @@
import matplotlib.pyplot as plt
import seaborn as sns
def plot_histogram(data, column):
fig, ax = plt.subplots()
ax.hist(data[column].dropna(), bins=20, edgecolor='k')
ax.set_title(f"Histogram of {column}")
ax.set_xlabel(column)
ax.set_ylabel("Frequency")
return fig
def plot_boxplot(data, column):
fig, ax = plt.subplots()
sns.boxplot(data=data, x=column, ax=ax)
ax.set_title(f"Boxplot of {column}")
return fig